@huggingface/tasks 0.2.0 → 0.2.1

package/dist/index.d.ts

@@ -37,12 +37,13 @@ declare enum ModelLibrary {
     "stanza" = "Stanza",
     "fasttext" = "fastText",
     "stable-baselines3" = "Stable-Baselines3",
-    "ml-agents" = "ML-Agents",
+    "ml-agents" = "Unity ML-Agents",
     "pythae" = "Pythae",
-    "mindspore" = "MindSpore"
+    "mindspore" = "MindSpore",
+    "unity-sentis" = "Unity Sentis"
 }
 type ModelLibraryKey = keyof typeof ModelLibrary;
-declare const ALL_DISPLAY_MODEL_LIBRARY_KEYS: ("speechbrain" | "fastai" | "adapter-transformers" | "allennlp" | "asteroid" | "bertopic" | "diffusers" | "doctr" | "espnet" | "fairseq" | "flair" | "keras" | "k2" | "mlx" | "nemo" | "open_clip" | "paddlenlp" | "peft" | "pyannote-audio" | "sample-factory" | "sentence-transformers" | "setfit" | "sklearn" | "spacy" | "span-marker" | "tensorflowtts" | "timm" | "transformers" | "transformers.js" | "stanza" | "fasttext" | "stable-baselines3" | "ml-agents" | "pythae" | "mindspore")[];
+declare const ALL_DISPLAY_MODEL_LIBRARY_KEYS: ("speechbrain" | "fastai" | "adapter-transformers" | "allennlp" | "asteroid" | "bertopic" | "diffusers" | "doctr" | "espnet" | "fairseq" | "flair" | "keras" | "k2" | "mlx" | "nemo" | "open_clip" | "paddlenlp" | "peft" | "pyannote-audio" | "sample-factory" | "sentence-transformers" | "setfit" | "sklearn" | "spacy" | "span-marker" | "tensorflowtts" | "timm" | "transformers" | "transformers.js" | "stanza" | "fasttext" | "stable-baselines3" | "ml-agents" | "pythae" | "mindspore" | "unity-sentis")[];
 
 declare const MODALITIES: readonly ["cv", "nlp", "audio", "tabular", "multimodal", "rl", "other"];
 type Modality = (typeof MODALITIES)[number];

package/dist/index.js

@@ -527,6 +527,13 @@ transcriptions = asr_model.transcribe(["file.wav"])`
   }
 };
 var mlAgents = (model) => [`mlagents-load-from-hf --repo-id="${model.id}" --local-dir="./downloads"`];
+var sentis = (model) => [
+  `string modelName = "[Your model name here].sentis";
+Model model = ModelLoader.Load(Application.streamingAssetsPath + "/" + modelName);
+IWorker engine = WorkerFactory.CreateWorker(BackendType.GPUCompute, model);
+// Please see provided C# file for more details
+`
+];
 var mlx = (model) => [
   `pip install huggingface_hub hf_transfer
 
@@ -749,10 +756,16 @@ var MODEL_LIBRARIES_UI_ELEMENTS = {
   "ml-agents": {
     btnLabel: "ml-agents",
     repoName: "ml-agents",
-    repoUrl: "https://github.com/huggingface/ml-agents",
+    repoUrl: "https://github.com/Unity-Technologies/ml-agents",
     docsUrl: "https://huggingface.co/docs/hub/ml-agents",
     snippets: mlAgents
   },
+  "unity-sentis": {
+    btnLabel: "unity-sentis",
+    repoName: "unity-sentis",
+    repoUrl: "https://github.com/Unity-Technologies/sentis-samples",
+    snippets: sentis
+  },
   pythae: {
     btnLabel: "pythae",
     repoName: "pythae",
@@ -4618,9 +4631,10 @@ var ModelLibrary = /* @__PURE__ */ ((ModelLibrary2) => {
   ModelLibrary2["stanza"] = "Stanza";
   ModelLibrary2["fasttext"] = "fastText";
   ModelLibrary2["stable-baselines3"] = "Stable-Baselines3";
-  ModelLibrary2["ml-agents"] = "ML-Agents";
+  ModelLibrary2["ml-agents"] = "Unity ML-Agents";
   ModelLibrary2["pythae"] = "Pythae";
   ModelLibrary2["mindspore"] = "MindSpore";
+  ModelLibrary2["unity-sentis"] = "Unity Sentis";
   return ModelLibrary2;
 })(ModelLibrary || {});
 var ALL_MODEL_LIBRARY_KEYS = Object.keys(ModelLibrary);

package/dist/index.mjs

@@ -493,6 +493,13 @@ transcriptions = asr_model.transcribe(["file.wav"])`
   }
 };
 var mlAgents = (model) => [`mlagents-load-from-hf --repo-id="${model.id}" --local-dir="./downloads"`];
+var sentis = (model) => [
+  `string modelName = "[Your model name here].sentis";
+Model model = ModelLoader.Load(Application.streamingAssetsPath + "/" + modelName);
+IWorker engine = WorkerFactory.CreateWorker(BackendType.GPUCompute, model);
+// Please see provided C# file for more details
+`
+];
 var mlx = (model) => [
   `pip install huggingface_hub hf_transfer
 
@@ -715,10 +722,16 @@ var MODEL_LIBRARIES_UI_ELEMENTS = {
   "ml-agents": {
     btnLabel: "ml-agents",
     repoName: "ml-agents",
-    repoUrl: "https://github.com/huggingface/ml-agents",
+    repoUrl: "https://github.com/Unity-Technologies/ml-agents",
     docsUrl: "https://huggingface.co/docs/hub/ml-agents",
     snippets: mlAgents
   },
+  "unity-sentis": {
+    btnLabel: "unity-sentis",
+    repoName: "unity-sentis",
+    repoUrl: "https://github.com/Unity-Technologies/sentis-samples",
+    snippets: sentis
+  },
   pythae: {
     btnLabel: "pythae",
     repoName: "pythae",
@@ -4584,9 +4597,10 @@ var ModelLibrary = /* @__PURE__ */ ((ModelLibrary2) => {
   ModelLibrary2["stanza"] = "Stanza";
   ModelLibrary2["fasttext"] = "fastText";
   ModelLibrary2["stable-baselines3"] = "Stable-Baselines3";
-  ModelLibrary2["ml-agents"] = "ML-Agents";
+  ModelLibrary2["ml-agents"] = "Unity ML-Agents";
   ModelLibrary2["pythae"] = "Pythae";
   ModelLibrary2["mindspore"] = "MindSpore";
+  ModelLibrary2["unity-sentis"] = "Unity Sentis";
   return ModelLibrary2;
 })(ModelLibrary || {});
 var ALL_MODEL_LIBRARY_KEYS = Object.keys(ModelLibrary);

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@huggingface/tasks",
   "packageManager": "pnpm@8.10.5",
-  "version": "0.2.0",
+  "version": "0.2.1",
   "description": "List of ML tasks for huggingface.co/tasks",
   "repository": "https://github.com/huggingface/huggingface.js.git",
   "publishConfig": {

package/src/library-ui-elements.ts

@@ -541,6 +541,14 @@ transcriptions = asr_model.transcribe(["file.wav"])`,
 
 const mlAgents = (model: ModelData) => [`mlagents-load-from-hf --repo-id="${model.id}" --local-dir="./downloads"`];
 
+const sentis = (model: ModelData) => [
+	`string modelName = "[Your model name here].sentis";
+Model model = ModelLoader.Load(Application.streamingAssetsPath + "/" + modelName);
+IWorker engine = WorkerFactory.CreateWorker(BackendType.GPUCompute, model);
+// Please see provided C# file for more details
+`
+];
+
 const mlx = (model: ModelData) => [
 	`pip install huggingface_hub hf_transfer
 
@@ -770,10 +778,16 @@ export const MODEL_LIBRARIES_UI_ELEMENTS: Partial<Record<ModelLibraryKey, Librar
 	"ml-agents": {
 		btnLabel: "ml-agents",
 		repoName: "ml-agents",
-		repoUrl: "https://github.com/huggingface/ml-agents",
+		repoUrl: "https://github.com/Unity-Technologies/ml-agents",
 		docsUrl: "https://huggingface.co/docs/hub/ml-agents",
 		snippets: mlAgents,
 	},
+	"unity-sentis": {
+		btnLabel: "unity-sentis",
+		repoName: "unity-sentis",
+		repoUrl: "https://github.com/Unity-Technologies/sentis-samples",
+		snippets: sentis,
+	},
 	pythae: {
 		btnLabel: "pythae",
 		repoName: "pythae",

package/src/model-libraries.ts

@@ -37,9 +37,10 @@ export enum ModelLibrary {
 	"stanza" = "Stanza",
 	"fasttext" = "fastText",
 	"stable-baselines3" = "Stable-Baselines3",
-	"ml-agents" = "ML-Agents",
+	"ml-agents" = "Unity ML-Agents",
 	"pythae" = "Pythae",
 	"mindspore" = "MindSpore",
+	"unity-sentis" = "Unity Sentis",
 }
 
 export type ModelLibraryKey = keyof typeof ModelLibrary;

package/src/tasks/mask-generation/data.ts

@@ -0,0 +1,18 @@
+import type { TaskDataCustom } from "..";
+
+const taskData: TaskDataCustom = {
+	datasets: [],
+	demo: {
+		inputs: [],
+		outputs: [],
+	},
+	metrics: [],
+	models: [],
+	spaces: [],
+	summary:
+		"Mask generation is creating a binary image that identifies a specific object or region of interest in an input image. Masks are often used in segmentation tasks, where they provide a precise way to isolate the object of interest for further processing or analysis.",
+	widgetModels: [],
+	youtubeId: "",
+};
+
+export default taskData;

package/src/tasks/zero-shot-object-detection/about.md

@@ -0,0 +1,39 @@
+## Use Cases
+
+### Object Search
+
+Zero-shot object detection models can be used in image search. Smartphones, for example, use zero-shot object detection models to detect entities (such as specific places or objects) and allow the user to search for the entity on the internet.
+
+### Object Counting
+
+Zero-shot object detection models are used to count instances of objects in a given image. This can include counting the objects in warehouses or stores or the number of visitors in a store. They are also used to manage crowds at events to prevent disasters.
+
+## Inference
+
+You can infer with zero-shot object detection models through the `zero-shot-object-detection` pipeline. When calling the pipeline, you just need to specify a path or HTTP link to an image and the candidate labels.
+
+```python
+from transformers import pipeline
+from PIL import Image
+
+image = Image.open("my-image.png").convert("RGB")
+
+detector = pipeline(model="google/owlvit-base-patch32", task="zero-shot-object-detection")
+
+predictions = detector(
+    image,
+    candidate_labels=["a photo of a cat", "a photo of a dog"],
+)
+
+# [{'score': 0.95,
+#   'label': 'a photo of a cat',
+#   'box': {'xmin': 180, 'ymin': 71, 'xmax': 271, 'ymax': 178}},
+#   ...
+# ]
+```
+
+# Useful Resources
+
+- [Zero-shot object detection task guide](https://huggingface.co/docs/transformers/tasks/zero_shot_object_detection)
+
+This page was made possible thanks to the efforts of [Victor Guichard](https://huggingface.co/VictorGuichard)

package/src/tasks/zero-shot-object-detection/data.ts

@@ -0,0 +1,57 @@
+import type { TaskDataCustom } from "..";
+
+const taskData: TaskDataCustom = {
+	datasets: [],
+	demo: {
+		inputs: [
+			{
+				filename: "zero-shot-object-detection-input.jpg",
+				type: "img",
+			},
+			{
+				label: "Classes",
+				content: "cat, dog, bird",
+				type: "text",
+			},
+		],
+		outputs: [
+			{
+				filename: "zero-shot-object-detection-output.jpg",
+				type: "img",
+			},
+		],
+	},
+	metrics: [
+		{
+			description:
+				"The Average Precision (AP) metric is the Area Under the PR Curve (AUC-PR). It is calculated for each class separately",
+			id: "Average Precision",
+		},
+		{
+			description: "The Mean Average Precision (mAP) metric is the overall average of the AP values",
+			id: "Mean Average Precision",
+		},
+		{
+			description:
+				"The APα metric is the Average Precision at the IoU threshold of a α value, for example, AP50 and AP75",
+			id: "APα",
+		},
+	],
+	models: [
+		{
+			description: "Solid zero-shot object detection model that uses CLIP as backbone.",
+			id: "google/owlvit-base-patch32",
+		},
+		{
+			description: "The improved version of the owlvit model.",
+			id: "google/owlv2-base-patch16-ensemble",
+		},
+	],
+	spaces: [],
+	summary:
+		"Zero-shot object detection is a computer vision task to detect objects and their classes in images, without any prior training or knowledge of the classes. Zero-shot object detection models receive an image as input, as well as a list of candidate classes, and output the bounding boxes and labels where the objects have been detected.",
+	widgetModels: [],
+	youtubeId: "",
+};
+
+export default taskData;